Implementation:Openai Openai python Response Incomplete Event
| Knowledge Sources | |
|---|---|
| Domains | API_Types, Responses_API |
| Last Updated | 2026-02-15 00:00 GMT |
Overview
Concrete streaming event type for signaling that a response finished as incomplete provided by the openai-python SDK.
Description
ResponseIncompleteEvent is a Pydantic model emitted when a response finishes as incomplete. It carries a response field containing the full Response object that was incomplete, a sequence_number for event ordering, and a type field always set to "response.incomplete". This event indicates that the model stopped generating before the response was fully complete, which may occur due to token limits, content filtering, or other constraints.
Usage
Import this type when building streaming event handlers that need to detect incomplete responses and take corrective action, such as retrying the request or notifying the user.
Code Reference
Source Location
- Repository: openai-python
- File: src/openai/types/responses/response_incomplete_event.py
Signature
class ResponseIncompleteEvent(BaseModel):
"""An event that is emitted when a response finishes as incomplete."""
response: Response
sequence_number: int
type: Literal["response.incomplete"]
Import
from openai.types.responses import ResponseIncompleteEvent
I/O Contract
Fields
| Name | Type | Required | Description |
|---|---|---|---|
| response | Response | Yes | The response that was incomplete. |
| sequence_number | int | Yes | The sequence number of this event. |
| type | Literal["response.incomplete"] | Yes | The type of the event. Always response.incomplete.
|
Usage Examples
import openai
client = openai.OpenAI()
stream = client.responses.create(
model="gpt-4o",
input="Write a very long essay about the history of computing.",
stream=True,
)
for event in stream:
if event.type == "response.incomplete":
print("Response was incomplete!")
print(f"Response ID: {event.response.id}")
print(f"Status: {event.response.status}")